2023
DOI: 10.1016/j.compscitech.2023.110095
|View full text |Cite
|
Sign up to set email alerts
|

A predictive model for the relationship between processing conditions and properties of thermoplastic vulcanizates (TPVs) via machine learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 9 publications
(2 citation statements)
references
References 44 publications
0
2
0
Order By: Relevance
“…Polymer composites have a significant impact on various engineering fields, including electronic devices, energy storage, and power delivery. In addressing the challenge of materials design, attention has shifted toward data-driven approaches within the realm of polymer informatics. There has also been progress for polymer composites, , including machine learning (ML) predictions of thermal and electrical properties and efficient utilization of composite materials database based on polymer, filler, and processing information. Moreover, several studies have demonstrated the effectiveness of features related not only to material composition but also to processing and measurement conditions, including filler shape, filler dispersion, and sample shape, in improving model performance. The incorporation of these additional features is anticipated to explain the inherent variability in experimental values of material properties, especially in the case of complex materials such as polymer composites.…”
Section: Introductionmentioning
confidence: 99%
“…Polymer composites have a significant impact on various engineering fields, including electronic devices, energy storage, and power delivery. In addressing the challenge of materials design, attention has shifted toward data-driven approaches within the realm of polymer informatics. There has also been progress for polymer composites, , including machine learning (ML) predictions of thermal and electrical properties and efficient utilization of composite materials database based on polymer, filler, and processing information. Moreover, several studies have demonstrated the effectiveness of features related not only to material composition but also to processing and measurement conditions, including filler shape, filler dispersion, and sample shape, in improving model performance. The incorporation of these additional features is anticipated to explain the inherent variability in experimental values of material properties, especially in the case of complex materials such as polymer composites.…”
Section: Introductionmentioning
confidence: 99%
“…This trend has been further accelerated by initiatives like the “Materials Genome Initiative”, which was proposed in 2011 and has spurred increased research and development in applying ML techniques in polymer materials . The conventional approaches to material investigation typically entail costly and time-consuming experimental phases or necessitate intricate and arduous computations, whereas machine learning can readily address certain aspects of these challenges. , To illustrate, the application of ML models has become increasingly prevalent in the prediction of molecular properties and the generation of force fields for MD simulations. Furthermore, ML models are increasingly garnering attention in the realm of bioinspired composites …”
Section: Introductionmentioning
confidence: 99%